- Conduid
- Marketplace
- #vector-search
MCP servers tagged vector-search
546 live MCP servers tagged "vector-search", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with vector-search.
Agent Code Intel
Local-first code intelligence for AI coding agents on macOS. One command wires semantic code search (GrepAI + Ollama + Qdrant) and a call-graph index (GitNexus) into Claude Code a…
Memory Lattice
Best AI Memory Layer for Claude Code and MCP Agents in 2026
Springai MCP
Sprinig AI MCP demo with MongoDB
Treq
TREQ - MCP Tool Ranking, Retrieval, and Efficient Querying
Applied AI
Modular Python libraries for applied AI: chunking, LLM generation, retrieval, keyword extraction, MCP client, and Slack search.
Senate Rag
A Retrieval‑Augmented Generation stack for Romanian legislative documents.
LLM Memory
Persistent, cross-model memory for LLM assistants — MCP server in .NET 10 over Postgres + pgvector + Apache AGE. Hybrid retrieval (vector + BM25 + graph PPR + LLM rerank), bi-temp…
Vector Core
Shared vector search infrastructure for MCP servers — embeddings, hybrid search, Qdrant storage, and more
Dewie
Agent-native retrieval over a self-enriching corpus: hybrid search + graph navigation exposed as MCP tools, so small models can punch above their weight.
dfrancislyondflabc-tech/agentic-recall
bad match as though it were one. Embedding model runs locally, nothing leaves the machine. MIT.
Ragnite
Confidence-Aware RAG Memory Engine for LLMs and coding agents - typed memory (facts, decisions, episodes, code), confidence scoring with answer modes, context packing, semantic ca…
Persistent Agent Memory
MCP server for persistent agent memory across sessions — semantic search, typed memories, session handoffs, directory indexing
Unified AI Memory
Offline-first AI memory for coding agents — one Markdown brain on your machine, shared via a local MCP server, with ONNX semantic search, RAG chat and a human-brain memory lifecyc…
Pinecone MCP Server
Custom MCP server exposing Pinecone vector search as an agentic-search tool for AI agents. Built with Node.js, TypeScript, and OpenRouter. Deployed on Railway.
Personal GraphRAG
Self-hosted GraphRAG for personal memory — Claude writes the entities and the edges directly over MCP, no second extraction model. Journal-first durability, optional local stack.
Fleetmem
Self-hosted, governed long-term memory for a fleet of AI agents — MCP-native, with hybrid retrieval, a typed knowledge graph, and per-agent mTLS access control. Runs on your own h…
Local Lore
Offline memory layer for Claude Code that indexes local session history and enables fast hybrid search (keyword + semantic) via a secure, fully offline Docker runtime.
Devbase
The open-source World Model Compiler for developer workspaces. One engine for code context, knowledge memories, and agent reasoning — replacing fragmented repo managers, note-taki…
Super Kb
Local MCP knowledge base for Claude Code that turns .skb/ folders into searchable project context.
AetherDB
AI-native database with semantic search, GraphRAG, hybrid search, full-text search, and edge deployment on Cloudflare Workers
Prasad Portfolio
VP / Head of AI Engineering portfolio — 14 production AI demos, governance-first architecture. prasadkavuri.com
Rag Analytics Dashboard
RAG Pipeline Analytics & Knowledge Base Monitor | Embedding visualisation, retrieval quality heatmaps & MCP tracking | Plotly.js
Evidence Lens
EvidenceLens is a modern AI-enabled research platform for indexing, searching, and analyzing scientific literature. It combines vector search, document retrieval, and citation-awa…
Kiro Ception
Kiro MCP Power that gives Kiro long-term memory. Indexes all CLI and IDE conversations into a semantic search engine using local or API-based embeddings. Newest-first indexing, le…
Google Cloud Genai Academy Apac Cohort 3
A security-first engineering portfolio from Google Cloud Gen AI Academy APAC Cohort 3, exploring how AI agents are grounded, connected to data and tools, deployed on Cloud Run, an…
Web Vector
Web research for AI agents in one tool call: search → read the full pages → rank → cited passages. Library, MCP server and CLI; zero API keys needed.
Semidx
Self-hosted semantic code search for your code and documents
Nivara AI
The AI support layer for Nivara Desk: answers what it can safely answer, asks when a request is ambiguous, and escalates the rest to a human. Python, FastAPI and Qdrant, with hybr…
Castalia
Indexa a documentação do seu sistema (Markdown, HTML, PDF, reST) e a entrega a agentes de IA via MCP, para que cenários de teste sejam escritos a partir das regras documentadas.
Filament AI
Generic, configuration-driven RAG toolkit for Laravel: chunking, embeddings, pgvector retrieval, grounded answering, an MCP server and a Filament control panel.
jaggernaut007/Nexus-MCP
Hybrid search (vector + BM25 + code graph) with structural code graph analysis and persistent semantic memory in a single local server. 10 tools, <350MB RAM, fully local, no API k…
Memorycore AI For Codex
MemoryCore Ai - For Codex: persistent memory via MCP with a 24-hour idle window for delayed memory consolidation, TurboVec semantic search and source-checked context to reduce tok…
Contextator
Turn any collection of documentation into a private, semantically searchable MCP endpoint — one URL per project, self-hosted in one Docker container.
Dexicon
Semantic search over your own code, documents and git history, for coding agents over MCP. One container on your machine: local embeddings with Ollama, hybrid search with Qdrant,…
Zmem
Local-first, agent-oriented memory substrate for engineering decisions and evolving project context
Context Chronicler
Subconscious Memory 2026: AI Coding Context Engine with Hybrid Semantic Search & MCP
FlowRAG
🌊 TypeScript RAG library with knowledge graph support — batch indexing, semantic search, entity extraction, and graph traversal. Lambda-friendly, Git-friendly, zero servers.
N8n MCP Server Agentic Rag
AI-powered chat app that searches course transcripts using Pinecone vector search and Gemini Flash 2.5 via OpenRouter. Evolved from an n8n MCP architecture to a fully owned stack.
Vacancy Radar
A local-first job application tracker. A markdown vault is the source of truth; a derived LanceDB index provides hybrid BM25 + vector search; an MCP server exposes read/write tool…
Enterprise AI Platform V2
Production-architecture RAG + AI agent platform on a free local stack — PySpark, DuckDB, FAISS, LangGraph, Ollama, FastMCP
Agentops Research Intelligence
Production-oriented multi-agent research intelligence platform combining LangGraph orchestration, Model Context Protocol (MCP), hybrid vector retrieval, claim verification, and ev…
Nexora
Agent-native data layer — SQLite by default, Postgres when you need scale, 38 MCP tools, structured memory, webhooks, data import/export
Semantic Code Intelligence
Local-first semantic code search with FAISS, BM25, cross-encoder reranking, reliability scoring, and cited walkthroughs.
REEL FINDER
Full-stack movie discovery and recommendation system with LLM tool calling, semantic search, and interaction-based personalization.
Mongodb Atlas Hackathon
Team workspace for the MongoDB × Cerebral Valley Harness Engineering Hackathon: resources, MCP + Agent Skills config, Atlas Vector Search memory starter
Memory LanceDB Pro
Full memory-lancedb-pro memory enhancement system for Claude Code via MCP protocol — hybrid retrieval, smart extraction, auto-capture, intelligent forgetting, multi-scope isolatio…
Rag DB Advisor
An evidence-based advisor for RAG stack decisions — every claim backed by rag-retriever-bench measurements. MCP + CLI.
Envri MCP Connector
Euro-Argo float metadata + OSO ontology in one Elasticsearch index, embedded for RAG and served via an HTTP API and an MCP server.
Markdown Memory
MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API…
Ctxdb
A context database for LLMs: structured storage and hybrid retrieval (BM25 + vectors, RRF-fused, token-budgeted) over SQLite, exposed to Claude as an MCP server